QSAR Applicability Domain Estimation by Projection of the Training Set in Descriptor Space: A Review

By Joanna Jaworska, N. Nikolova-Jeliazkova, T. Aldenberg. Alternatives to laboratory animals : ATLA, 2005

621 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Media Technology, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/7d4badd8386b0cff911c1c9b53b0543d042af79b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Kamel Mansouri
2. Roberto Todeschini
3. Viviana Consonni
4. Davide Ballabio
5. Binh Thai Pham
6. Menad Nait Amar
7. Ivan Gutman
8. Bo Zhou

In Molecular Biology

1. Viviana Consonni
2. Roberto Todeschini

Citations in the corpus

• Modeling viscosity of CO2 at high temperature and pressure conditions (2020, methodology): “The Hat matrix is calculated using the formula below (Kamari et al., 2015; Jaworska et al., 2005): H¼XðXtXÞ 1Xt (23) with X represents an (n � d) matrix, n and d denote the dimension and the data points number, respectively, and Xt is the transpose matrix of X.”
• Comparison of Different Approaches to Define the Applicability Domain of QSAR Models (2012, methodology): “They can be classified into following four major categories based on the methodology used for interpolation space characterization in the model descriptor space: Range-based methods, Geometric methods, Distancebased methods and Probability Density Distribution based methods [1–5].”